Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90160
    Prev
    Next
    INDEX
    Explanations

    Back pressure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     homosexual
    -0.08
     scars
    -0.08
     structural
    -0.07
    asen
    -0.07
     Oz
    -0.07
     действие
    -0.07
     vị
    -0.07
     disclaimer
    -0.07
     MPs
    -0.07
     apostas
    -0.07
    POSITIVE LOGITS
    生产
    0.12
    Producer
    0.12
     producer
    0.11
     Feeding
    0.11
     bott
    0.11
     downstream
    0.11
     producteurs
    0.11
     생산
    0.11
     Conveyor
    0.11
    producer
    0.11
    Activations Density 0.012%

    No Known Activations